Retrieving the syntactic structure of erroneous ASR transcriptions for open-domain Spoken Language Understanding

Abstract

Retrieving the syntactic structure of erroneous ASR transcriptions can be of great interest for open-domain Spoken Language Understanding tasks in order to correct or at least reduce the impact of ASR errors on final applications. Most of the previous works on ASR and syntactic parsing have addressed this problem by using syntactic features during ASR to help reducing Word Error Rate (WER). The improvement obtained is often rather small, however the structure and the relations between words obtained through parsing can be of great interest for the SLU processes, even without a significant decrease of WER. That is why we adopt another point of view in this paper: considering that ASR transcriptions contain inevitably some errors, we show in this study that it is possible to improve the syntactic analysis of these erroneous transcriptions by performing a joint error detection / syntactic parsing process. The applicative framework used in this study is a speech-to-speech system developed through the DARPA BOLT project.

SemEval-2014 Task 2: Grammar Induction for Spoken Dialogue Systems

“…For example, if web corpora are used to extract the candidate fragments grammatical mistakes and out-of-domain sentences might appear. Similarly, if the transcriptions from a deployed SDS system are used for grammar induction, transcription errors might introduce noise (Bechet et al, 2014).…”